© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 8718
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving common factors and divisors

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    255
    +0.16
    0.9%
    78
    +0.16
    0.9%
    200
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    209
    +0.16
    0.04
    305
    +0.16
    0.03
    200
    +0.13
    0.03
    Negative Logits
    .";
    -2.09
     ();
    -1.83
    ';
    -1.53
    ";
    -1.50
     (>
    -1.48
     ";
    -1.45
    ulating
    -1.44
     '';
    -1.42
     {};
    -1.41
    fully
    -1.30
    POSITIVE LOGITS
    )
    2.69
    )*
    2.68
    )."
    2.64
    ))/(-
    2.62
    )*-
    2.61
    __)
    2.57
    )?
    2.54
    )/
    2.53
    )</
    2.50
    )].
    2.46
    Activations Density 0.067%

    No Known Activations